AI Edge Computing Chips and Solutions
In an era where every millisecond counts, waiting for the cloud is no longer an option. Our AI Edge computing chips bring high-performance neural processing directly to the hardware. Our chips target the key requirements of low latency, high computing power, and low power consumption. Integrating advanced process technology and AI acceleration architecture, we provide full-stack solutions spanning from chips to software suites, enabling real-time data processing and decision-making at the edge without relying on the cloud. Our AI edge computing chips enable instant data processing at the source, delivering unmatched speed and privacy.
The chip adopts an XPU hybrid architecture, integrating CPU, GPU, NPU cores and AI acceleration engines. It is compatible with mainstream deep learning frameworks and supports edge deployment of AI large models with over 1 billion parameters.
Equipped with ULP technology, its power consumption is as low as the milliwatt level. It natively supports TSN, with end-to-end latency controlled at the microsecond level.
The supporting software suite helps customers achieve rapid deployment. Our products are widely used in intelligent manufacturing, smart transportation, humanoid robots and other fields, driving the implementation of edge intelligence scenarios.
